필터 결과
236개정렬
1:09:09EN
Cognitive Revolution "How AI Changes Everything"· 2024년 10월 2일팟캐스트30 Percent on SWE-bench: Cosine Taught Genie How Engineers Actually Think진행자 Nathan LabenzAlistair Pullen tells Latent Space how Cosine reconstructed human problem-solving, fine-tuned on billions of tokens, and took the top score on software engineering’s hardest public test.
16:57EN
Matthew Berman· 2024년 9월 30일Jensen Huang and Marc Benioff on AI Agents and the Future of ComputingMatthew Berman, Jensen Huang, Marc Benioff · Forward FutureMatthew Berman comments on a 2024 Dreamforce discussion about agent collaboration, training, safety, and making AI tools practical.
48:31EN
No Priors: AI, Machine Learning, Tech, & Startups· 2024년 9월 19일팟캐스트 · 2명A Call Center Contact Costs $13. A Company Agent Can Do It for Under a Dollar진행자 Sarah Guo, Elad GilSierra cofounder and OpenAI chairman Bret Taylor tells No Priors why branded customer agents are shovel-ready, why RAG demos are not products, and how AI software should charge for the job done.
2:03:55ENCognitive Revolution "How AI Changes Everything"· 2024년 9월 18일팟캐스트The More You Constrain an Agent, the More You Can Trust It진행자 Nathan LabenzAgent.ai engineering lead Andrei Oprisan tells Nathan Labenz why narrow, highly prescribed workflows beat open-ended autonomy — and how a 12-person team shipped a free agent network past 40,000 users in a few months.
1:12:31EN
Sequoia Capital· 2024년 8월 27일팟캐스트A Bare Model Closes 35% of Airline Changes. Sierra's Agents Clear 70% of Real Tickets.Clay Bavor on why putting a raw LLM in front of customers does not math, and how AgentOS, supervisor agents, and outcome pricing change the arithmetic.
9:58ENMatthew Berman· 2024년 8월 2일Abstract AI: A Proposed Routing Layer for Language ModelsMatthew Berman · Forward FutureMatthew Berman outlines a startup idea for choosing models and workflows by cost, speed and quality.
1:07:05ENSequoia Capital· 2024년 7월 16일팟캐스트AlphaGo Combined Learning and Search. Language Models Only Did the First Half.Reflection AI's Misha Laskin tells Sequoia why prompted coding agents stall in the teens, and why the missing piece is still a ground-truth reward.
1:16:22ENCognitive Revolution "How AI Changes Everything"· 2024년 7월 9일팟캐스트He Spent 20 Hours Crafting a Prompt. DSPy Beat Him Anyway진행자 Nathan LabenzSander Schulhoff walks through The Prompt Report — a 78-page survey of what actually works when you prompt large language models.
59:11ENSequoia Capital· 2024년 6월 25일팟캐스트Don't Train a Model. Factory's Founders Say Go Dig for GoldMatan Grinberg and Eno Reyes tell Sequoia's Training Data why they sell a fleet of job-specific droids on top of other people's models — and how that stack just took SWE-bench from 14% to 19%.
1:37:07ENCognitive Revolution "How AI Changes Everything"· 2024년 6월 22일팟캐스트A Text-Only AI Outdiagnosed GPs. Google Still Won't Ship It.진행자 Nathan LabenzGoogle researchers Vivek Natarajan and Khaled Saab walk Nathan Labenz through five medical-AI papers, from radiology reports to an AI doctor that still has to earn trust.
49:50ENSequoia Capital· 2024년 6월 18일팟캐스트Unconstrained agents captivated Twitter. Custom ones are what ship.LangChain founder Harrison Chase tells Sequoia’s Training Data what an agent actually is, why AutoGPT stalled, and which cognitive architectures reach production.
1:00ENMatthew Berman· 2024년 5월 13일Andrew Ng on Four Agentic AI Design PatternsMatthew Berman, Andrew Ng · Forward FutureA short excerpt identifies reflection, tools, planning and multi-agent collaboration as approaches to building AI agents.
29:28ENNo Priors: AI, Machine Learning, Tech, & Startups· 2024년 5월 2일팟캐스트 · 2명Devin Will Not Replace Engineers. It Will Multiply Them, Says Cognition’s Scott Wu진행자 Sarah Guo, Elad GilThe IOI champion behind Devin explains why an AI software engineer that you can watch over the shoulder creates more human engineers, not fewer.
16:22ENMatthew Berman· 2024년 5월 2일Harrison Chase on Planning, Interface Design and Memory for AI AgentsMatthew Berman, Harrison Chase · Forward FutureThe LangChain CEO outlines open questions for agent builders, with commentary from Matthew Berman on oversight, workflows and memory.
19:09ENMatthew Berman· 2024년 4월 28일OSWorld: Evaluating Computer-Use Agents in Real ApplicationsMatthew Berman · Forward FutureMatthew Berman explains the 2024 benchmark’s observation–action loop, task-specific checks and early results, with the limitations of its experimental setup.
19:46ENMatthew Berman· 2024년 4월 15일Building a CrewAI Financial-Analysis Team on Lightning AIMatthew Berman · Forward FutureMatthew Berman demonstrates a 2024 two-agent workflow, first using Groq and then connecting a cloud-hosted Ollama model.
13:59ENMatthew Berman· 2024년 4월 5일SWE-agent Tutorial: Navigating Repositories and Attempting GitHub FixesMatthew Berman, Carlos · Forward FutureMatthew Berman sets up a research coding agent, hits an installation problem and a cost limit, then shows an author’s successful SymPy benchmark example.
14:58ENMatthew Berman· 2024년 3월 30일OpenDevin’s Early Coding Agent: A 2024 Installation and DemoMatthew Berman · Forward FutureMatthew Berman installs an early open-source coding-agent project and tries a calculator and a simple web page, while encountering setup and browser issues.
23:47ENMatthew Berman· 2024년 3월 29일Andrew Ng’s Four Agentic Workflow Patterns, Explained by Matthew BermanMatthew Berman, Andrew Ng · Matthew BermanReflection, tools, planning and collaboration can turn a single model response into an iterative workflow, with reliability and cost tradeoffs.
27:32ENNo Priors: AI, Machine Learning, Tech, & Startups· 2024년 3월 28일팟캐스트 · 2명From a side project to 700 integrations: Harrison Chase on what still blocks agents진행자 Sarah Guo, Elad GilThe LangChain CEO walks through a two-year churn of patterns, and why memory, planning, and few-shot data still matter more than swapping models.
42:14ENNo Priors: AI, Machine Learning, Tech, & Startups· 2024년 3월 7일팟캐스트 · 2명Meta’s $197 Billion Day Was a Partial Answer to AI’s $200 Billion Question진행자 Sarah Guo, Elad GilSarah Guo and Elad Gil walk through Gemini, Mistral, NVIDIA’s upgrade cycle, Klarna’s support bot, and why the real AI spend still sits with the hyperscalers.
55:29ENMatthew Berman· 2024년 2월 24일Building a CrewAI Newsletter Team: Scraping, Summarizing and DebuggingMatthew Berman, Joe · Forward FutureMatthew Berman builds a two-agent newsletter prototype, works through input and scraping errors, and shows what still needs to be fixed.
4:56ENCognitive Revolution "How AI Changes Everything"· 2024년 2월 1일팟캐스트If the Mind Is a Tool, AI Looks Less Like a Threat진행자 Nathan LabenzYohei Nakajima and Nathan Labenz pause a TED AI talk to connect agent-building habits with East–West ideas of identity.
1:45:21ENCognitive Revolution "How AI Changes Everything"· 2024년 1월 30일팟캐스트600,000 Attack Prompts, and Nearly 40% Still Pwned GPT-4진행자 Nathan LabenzSander Schulhoff walks Nathan Labenz through the prompting habits that still work, the role-play myth that does not, and the global HackAPrompt contest that mapped how language models get hijacked.더 보기236개 중 24개 표시